Unsupervised incremental online adaptation to unknown environment and speaker

A Maximum Likelihood Spectral Transformation (MLST) technique is used for robust speech recognition under mis-matched training and testing conditions. The linear spectral speech feature vectors of testing utterances are transformed such that the likelihood of the utterances is increased after the transformation. The cepstral vectors are computed from the transformed spectra. The function used for the spectral transformation is designed to handle both convolutional and additive noise. Since the function has small number of parameters to be estimated, MLST requires only a few utterances for adaptation. Furthermore, the computation for parameter estimation and spectral transformation can be done efficiently in linear time. Therefore, the MLST is suitable for rapid online adaptation. To evaluate the efficiency of the MLST technique, it has been implemented for unsupervised incremental online adaptation. The system is tested on speaker-phone telephone speech data, and MLST reduces the error rate by 29.5% when used for speaker and environment adaptation.